Separating leaves from trunks and branches with dual-wavelength terrestrial lidar scanning

Ли, Жан; Douglas, Ewan S.; Strahler, Alan H.; Schaaf, Crystal B.; Yang, Xiaoyuan; Wang, Zhuosen; Yao, Tian; Zhao, Feng; Saenz, E. J.; Paynter, Ian; Woodcock, Curtis E.; Chakrabarti, Supriya; Cook, Timothy A.; Martel, Jason; Howe, Glenn A.; Jupp, David L.B.; Culvenor, Darius; Newnham, Glenn; Lovell, Jenny

doi:10.1109/igarss.2013.6723554

Cited by 22 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All these approaches rely on indirect separation using statistical properties of the scans and are not yet applicable to multiple return scanners. As previously discussed, full-waveform scanners provide additional information on target properties and new dual-wavelength scanners such as SALCA and DWEL provide a direct way to separate scene components with spectral information, as well as account for partial beam interception based on return energy from full-waveform recording and processing [89].…”

Section: Methods Developmentmentioning

confidence: 99%

Terrestrial Laser Scanning for Plot-Scale Forest Measurement

et al. 2015

Self Cite

View full text Add to dashboard Cite

Plot-scale measurements have been the foundation for forest surveys and reporting for over 200 years. Through recent integration with airborne and satellite remote sensing, manual measurements of vegetation structure at the plot scale are now the basis for landscape, continental and international mapping of our forest resources. The use of terrestrial laser scanning (TLS) for plot-scale measurement was first demonstrated over a decade ago, with the intimation that these instruments could replace manual measurement methods. This has not yet been the case, despite the unparalleled structural information that TLS can capture. For TLS to reach its full potential, these instruments cannot be viewed as a logical progression of existing plot-based measurement. TLS must be viewed as a disruptive technology that requires a rethink of vegetation surveys and their application across a wide range of disciplines. We review the development of TLS as a plotscale measurement tool, including the evolution of both instrument hardware and key data processing methodologies. We highlight two broad data modelling approaches of gap probability and geometrical modelling and the basic theory that underpins these. Finally, we discuss the future prospects for increasing the utilisation of TLS for plot-scale forest assessment and forest monitoring.

show abstract

Section: Methods Developmentmentioning

confidence: 99%

Terrestrial Laser Scanning for Plot-Scale Forest Measurement

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…Calders et al [23] have shown that the radiometrical calibration carried out for a specific scanner cannot be transferred to another scanner, which greatly limits the applicability of using intensity information for downstream processing. Various authors have made attempts to construct and use multi-wavelength laser scanning to exploit different material reflectance at different wavelengths [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Separating Tree Photosynthetic and Non-Photosynthetic Components from Point Cloud Data Using Dynamic Segment Merging

Wang

Brunner

et al. 2018

Forests

View full text Add to dashboard Cite

Many biophysical forest properties such as wood volume and leaf area index (LAI) require prior knowledge on either photosynthetic or non-photosynthetic components. Laser scanning appears to be a helpful technique in nondestructively quantifying forest structures, as it can acquire an accurate three-dimensional point cloud of objects. In this study, we propose an unsupervised geometry-based method named Dynamic Segment Merging (DSM) to identify non-photosynthetic components of trees by semantically segmenting tree point clouds, and examining the linear shape prior of each resulting segment. We tested our method using one single tree dataset and four plot-level datasets, and compared our results to a supervised machine learning method. We further demonstrated that by using an optimal neighborhood selection method that involves multi-scale analysis, the results were improved. Our results showed that the overall accuracy ranged from 81.8% to 92.0% with an average value of 87.7%. The supervised machine learning method had an average overall accuracy of 86.4% for all datasets, on account of a collection of manually delineated representative training data. Our study indicates that separating tree photosynthetic and non-photosynthetic components from laser scanning data can be achieved in a fully unsupervised manner without the need of training data and user intervention.

show abstract

“…However, intensity captured by a laser scanner needs an instrument specific radiometrical calibration before including it in further processing (Calders et al, 2017). Recently developed multi-wavelength (e.g., hyperspectal) scanners can help to better solve such a task (Li et al, 2013;Hakala et al, 2012;Vauhkonen et al, 2013). However, these scanners are still in an early development stage, and not yet widely available.…”

Section: Introductionmentioning

confidence: 99%

Feasibility of Machine Learning Methods for Separating Wood And Leaf Points From Terrestrial Laser Scanning Data

Wang

Hollaus

Pfeifer

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Classification of wood and leaf components of trees is an essential prerequisite for deriving vital tree attributes, such as wood mass, leaf area index (LAI) and woody-to-total area. Laser scanning emerges to be a promising solution for such a request. Intensity based approaches are widely proposed, as different components of a tree can feature discriminatory optical properties at the operating wavelengths of a sensor system. For geometry based methods, machine learning algorithms are often used to separate wood and leaf points, by providing proper training samples. However, it remains unclear how the chosen machine learning classifier and features used would influence classification results. To this purpose, we compare four popular machine learning classifiers, namely Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF), and Gaussian Mixture Model (GMM), for separating wood and leaf points from terrestrial laser scanning (TLS) data. Two trees, an Erytrophleum fordii and a Betula pendula (silver birch) are used to test the impacts from classifier, feature set, and training samples. Our results showed that RF is the best model in terms of accuracy, and local density related features are important. Experimental results confirmed the feasibility of machine learning algorithms for the reliable classification of wood and leaf points. It is also noted that our studies are based on isolated trees. Further tests should be performed on more tree species and data from more complex environments.

show abstract

Separating leaves from trunks and branches with dual-wavelength terrestrial lidar scanning

Cited by 22 publications

References 5 publications

Terrestrial Laser Scanning for Plot-Scale Forest Measurement

Terrestrial Laser Scanning for Plot-Scale Forest Measurement

Separating Tree Photosynthetic and Non-Photosynthetic Components from Point Cloud Data Using Dynamic Segment Merging

Feasibility of Machine Learning Methods for Separating Wood And Leaf Points From Terrestrial Laser Scanning Data

Contact Info

Product

Resources

About